con un clic
skills
skills contiene 31 skills recopiladas de jeckyl2010, con cobertura ocupacional por repositorio y páginas de detalle dentro del sitio.
Skills en este repositorio
Apply senior UI/UX judgment to interfaces, user flows, interaction details, and product usability decisions.
Build, review, and extend Astro static sites — config, integrations, SEO, deployment to GitHub Pages.
Design system, visual language, tone, and UI conventions for comtechconsulting.dk — reference before adding any new UI, copy, or page to the site.
Apply senior-level engineering judgment to code review, implementation, debugging, refactoring, and delivery planning.
Advise on Confluence Cloud AI — Atlassian Intelligence, Rovo Chat, Rovo Chat macro, plan tier detection, and space-level AI scoping.
Configure and surface Rovo AI features in Confluence Cloud — Chat, custom Agents, Space Agent assignment, and space homepage CTA patterns.
Bring a GitHub repo to professional standard — CI, security tooling, community health files, badges, Dependabot, CodeQL, and Scorecard.
Author, review, and fix Slidev presentations — visual inspection, design consistency, frontmatter hygiene, Carbon icons, rewrite vs patch decisions.
Analyse doc changes since the last CHANGELOG.md update and draft a major-change entry if the changes qualify.
Author and maintain Material for MkDocs sites — .pages nav, assets, frontmatter, Mermaid, admonitions, and Diátaxis structure.
Detect and fix AI writing patterns (slop). 45+ patterns across 3 severity tiers with scoring and an editor mode that fixes problems directly.
Review an unfamiliar codebase and produce a grounded design assessment with explicit judgment and pragmatic recommendations.
Apply senior architectural judgment to systems, boundaries, scalability, reliability, and technical decision-making.
Add SEO meta tags, Open Graph, Twitter Card, canonical URLs, sitemap, and a generated OG image to a static site.
Extract text from a local PDF on macOS when native Spotlight metadata is insufficient, using python3 and pypdf.
Audit project dependencies for outdated versions, known CVEs, licensing risk, orphaned packages, and upgrade paths across any package manifest format.
Generate Architecture Decision Records (MADR format) from design context, discussions, or review findings. Structured, auditable decision artifacts.
Review architecture documents for defensibility, boundary clarity, ownership, survivability, and testability. Works beyond manufacturing.
Write client-ready consulting deliverables: findings reports, architecture recommendations, executive summaries. Evidence-based, no fluff.
Structured debugging workflow — hypothesis-driven, evidence-based, reproducible. Produces auditable findings, not just a fix.
Senior IT/OT architect persona for brownfield manufacturing. ISA-95 layering, IEC 62443 security, multi-site target architecture, resilience-first.
Extract risk scenarios, control statements, evidence requirements, and ownership from architecture and governance documents into structured controls.
Author target-state architecture patterns and proposals with clear problem, constraints, recommendation, trade-offs, risks, ownership, and next step.
Remove AI writing patterns. Fixes 29 named tells: inflated significance, vague attribution, em dash overuse, AI vocabulary, soulless structure.
Extract decisions, action items, open questions, and key insights from meetings, transcripts, and workshops. Structured output, no padding.
Stress-test a plan or design by interviewing the user one question at a time, walking each decision-tree branch until shared understanding is reached.
Check a GitHub, GitLab, or Perforce PR/MR/CL for unresolved review comments, failing checks, and description gaps.
Strict code and test review against coding principles, minimality, and project specs. Reports KEEP/DISCARD/ESCALATE with quality score.
Turn any folder of files into a knowledge graph with community detection, interactive HTML, GraphRAG-ready JSON, and an audit report.
Iteratively improve a PR/MR/CL until Greptile gives 5/5 confidence with zero unresolved comments. Max 5 iterations.
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler while keeping full technical accuracy.